Abstract
Knowledge-based neural networks are concerned with the use of numerical information, which forms the domain knowledge, obtained from sensor measurements to determine the initial structure of a neural network. Research on combining symbolic inductive learning with neural networks, as well as research on combining fuzzy logic with neural networks, is proceeding on several fronts. Fuzzy decision trees and their various algorithmic implementations are one of the most popular choices in applications to learning and reasoning from feature-based examples. Such constructions have drawn increasing attention recently due to comprehensibility of the generated knowledge structure, and wide availability of data in the form of feature descriptions. However, the inability of coping with missing data, imprecise or vague information, and measurements errors create a lot of problems for symbolic artificial intelligence. These problems might be overcome by employing fuzzy methodology. In this paper we present an approach based on fuzzy neural trees for determining the structure of a neural network. An analysis of digital thallium-201 myocardial scintigraphs is presented to corroborate the theory and demonstrate the utility of the approach.
Preview
Unable to display preview. Download preview PDF.
References
P. Lippmann, An Introduction to Computing with Neural Nets, IEEE Acoustics, Speech, and Signal Processing 44 (1987) 4–22.
B. Irie and S. Miyake, Capabilities of Three-Layered Perceptrons, in: Proc. of IEEE Inter. Conf. on Neural Networks, (1988) 641–648.
S. Y. Kung and J. N. Hwang, An Algebraic Projection Analysis for Optimal Hidden Units Size and Learning Rates in Back-Propagation Learning, in: Proc. of IEEE Int. Conf. on Neural Networks, (1988) 363–370.
J. A. Sirat and J. P. Nadal, Neural Trees: a New Tool For Classification, Network 1 (1990) 423–438.
M. Bichsel and P. Seitz, Minimum Class Entropy: A Maximum Information Approach To Layered Networks, Neural Networks 2 (1989) 133–141.
J. R. Quinlan, Induction of Decision Trees, Machine Learning 1 (1986) 81–106.
T. G. Dietterich, H. Hild, and G. Bakiri, A Comparative Study of ID3 and Back-Propagation for English Text-to-Speech Mapping, in: Proc. of the 7th Int. Conference on Machine Learning, Texas (1990).
D. H. Fisher and K. B. Mckusick, An Empirical Comparison of ID3 and Back-Propagation, in: Proc. of the 11th Int. Conf. on AI, (1989) 788–793.
K. J. Cios and N. Liu, A Machine Learning Method for Generation of a Neural Network Architecture: A Continuous ID3 Algorithm, IEEE Neural Networks 2 (1992) 280–291.
S. E. Fahlman and C. Labiere, The Cascade-Correlation Learning Architecture, in Advances in Neural Information Processing Systems 2, D. S. Touretzky, Ed., (Morgan Kaufmann Publishers, Los Altos, 1990) 524–532.
L. M. Sztandera, Dynamically Generated Neural Network Architectures, J. of Artificial Neural Systems 1 (1994) 41–66.
L. A. Zadeh, Fuzzy Sets, Information and Control 8, (1965) 338–353.
A. D. Nelson, R. F. Leighton, L. T. Andrews, L. S. Goodenday, L. Yonovitz, and D. Thekdi, A Comparison of Methods for the Analysis of Stress Thallium-201 Scintigraphs, in: Proc. of the Comp. in Cardiology Conference, (1979) 315–318.
M. M. Gupta and J. Qi, On Fuzzy Neuron Models, in: Fuzzy Logic for the Management or Uncertainty, L. A. Zadeh and J. Kacprzyk, Eds., (John Wiley & Sons, Inc., New York, 1992) 479–491.
H. Ishibuchi, R. Fujioka, and H. Tanaka, Possibility and Necessity Pattern Classification Using Neural Networks, Fuzzy Sets and Systems 48, (1992) 331–340.
H. Ishibuchi, R. Fujioka, and H. Tanaka, Neural Networks that Learn from Fuzzy If-Then Rules, IEEE Fuzzy Systems 1 (2), (1993) 85–97.
J. M. Keller and H. Tahani, Backpropagation Neural Networks for Fuzzy Logic, Information Sciences 62, (1992) 205–221.
J. M. Keller, R. R. Yager, and H. Tahani, Neural Network Implementation of Fuzzy Logic, Fuzzy Sets and Systems 45, (1992) 1–12.
K. Hirota and W. Pedrycz, Fuzzy Logic Neural Networks: Design and Computations, in: Proc. of the IJCNN'91 (2), Singapore, (1991) 1588–1593.
Y. Hayashi, E. Czogala, and J. J. Buckley, Fuzzy Neural Controller, in: Proc. of 1st Int. Conference on Fuzzy and Neural Systems, San Diego, (1992) 197–202.
B. Kosko, Neural Networks and Fuzzy Systems, (Prentice Hall, Englewood Cliffs, 1992).
L. X. Wang and J. M. Mendel, Generating Fuzzy Rules by Learning from Examples, IEEE Systems, Man, and Cybernetics 22 (6), (1992) 1414–1427.
K. Hornik, Approximation Capabilities of Multilayer Feedforward Networks, Neural Networks 4, (1991) 251–257.
L. X. Wang, Fuzzy Systems are Universal Approximators, in: Proc. of 1st Int. 1 Conference on Fuzzy and Neural Systems, San Diego, (1992) 1163–1169.
J. Dombi, A General Class of Fuzzy Operators, the De Morgan Class of Fuzzy Operators and Fuzziness Measures, Fuzzy Sets and Systems 8, (1982) 149–163.
H. Szu and R. Hartley, Fast Simulated Annealing, Phys. Lett. A 122 (8) (1987) 157–162.
R. R.Yager, On Choosing Between Fuzzy Subsets, Kybernetes 9, (1980) 151–154.
S. Murakami, H. Maeda and S. Immamura, Fuzzy Decision Analysis on the Development of Centralized Regional Energy Control System, in: Preprints of IFAC Conference on Fuzzy Information, Knowledge Representation and Decision Analysis, (1983) 353–358.
L. M. Sztandera, A Comparative Study of Ranking Fuzzy Sets Defined by a Neural Network Algorithm — Justification for a Centroidal Method, Archives of Control Sciences 4 (1/2), (1995) 89–111.
L. M. Sztandera, Fuzzy Neural Trees, Information Sciences 90 (1/4), (1996) 155–177.
K. J. Cios, L.S. Goodenday, and L. M. Sztandera, Hybrid Intelligence Systems or Diagnosing Coronary Stenosis — Combining Fuzzy Generalized Operators with Decision Rules Generated by Machine Learning Algorithms, IEEE Engineering in Medicine and Biology 13 (5), (1994) 723–729.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sztandera, L.M. (1996). Knowledge-based fuzzy neural networks. In: RaÅ›, Z.W., Michalewicz, M. (eds) Foundations of Intelligent Systems. ISMIS 1996. Lecture Notes in Computer Science, vol 1079. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61286-6_159
Download citation
DOI: https://doi.org/10.1007/3-540-61286-6_159
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61286-5
Online ISBN: 978-3-540-68440-4
eBook Packages: Springer Book Archive